CN111310019B

CN111310019B - Information recommendation method, information processing method, system and equipment

Info

Publication number: CN111310019B
Application number: CN201811512112.XA
Authority: CN
Inventors: 肖蒴
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-12-11
Filing date: 2018-12-11
Publication date: 2023-10-20
Anticipated expiration: 2038-12-11
Also published as: CN111310019A

Abstract

The embodiment of the application provides an information recommendation method, an information processing system and information processing equipment. The information recommendation method comprises the following steps: acquiring biological characteristics of a user different from other people and scene information of the user; acquiring association information related to the user when the user is determined to be a registered user based on the biological characteristics; and recommending service information to the user according to the association information and the scene information. The technical scheme provided by the embodiment of the application meets the requirement that personalized recommendation can be carried out for each user when a plurality of users share one device; in addition, the technical scheme provided by the embodiment fully considers the scene information of the user when recommending the information, so that the recommended information has identification degree related to the scene information, and the accuracy of information recommendation is improved.

Description

Information recommendation method, information processing method, system and equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to an information recommendation method, an information processing system, and an information processing device.

Background

With the development of network technology and service information diversification, a large amount of new service information (such as news, articles, audio, video, etc.) appears in the field of view of users every day. The problem of how to solve the problem of recommending the most interesting content to the user in the shortest time of the user stay is faced, and how to solve the problem by using a more scientific method and system directly influences the user experience and is a key factor for improving the watching frequency and the watching duration of the user.

The existing personalized recommendation method mostly uses a device end/registration ID account number as granularity to give recommendation.

Disclosure of Invention

The embodiments of the present application provide an information recommendation method, an information processing method, a system and a device different from the prior art.

In one embodiment of the application, an information recommendation method is provided. The method comprises the following steps:

acquiring biological characteristics of a user different from other people and scene information of the user;

acquiring association information related to the user when the user is determined to be a registered user based on the biological characteristics;

and recommending service information to the user according to the association information and the scene information.

In another embodiment of the present application, an information recommendation method is provided. The method comprises the following steps:

Acquiring biological characteristics of a user, which are different from other people;

responding to the information acquisition request triggered by the user, and acquiring scene information when the request is triggered;

and sending the biological characteristics and the scene information to a server, so that the server recommends service information for the user according to the biological characteristics and the scene information.

In yet another embodiment of the present application, an information recommendation system is provided. The system comprises:

the client is used for acquiring biological characteristics of the user, which are different from other people; responding to the information acquisition request triggered by the user, and acquiring scene information when the request is triggered; the biological characteristics and the scene information are sent to a server;

the server side is used for acquiring association information related to the user when the user is determined to be a registered user based on the biological characteristics; and recommending service information to the user according to the association information and the scene information.

In yet another embodiment of the present application, an information recommendation method is provided. The system comprises:

When the user is determined to be a non-registered user based on the biological characteristics, building association information for the user according to the biological characteristics;

In yet another embodiment of the present application, an information processing method is provided. The method comprises the following steps:

acquiring multimedia information related to a user before and during service information display;

according to the multimedia information, determining the attention degree of a user watching the service information to the service information;

and sending the attention degree of the user to the service information to a server so as to update the portrait information of the user according to the attention degree of the user to the service information by the server.

In yet another embodiment of the present application, an electronic device is provided. The electronic device comprises a memory and a processor, wherein,

the memory is used for storing programs;

the processor, coupled to the memory, is configured to execute the program stored in the memory for:

In yet another embodiment of the present application, a client device is provided. The client device includes a memory and a processor, wherein,

the memory is used for storing programs;

In yet another embodiment of the present application, a client device is provided. The client device includes a memory and a processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory is used for storing programs;

collecting first multimedia information related to a user in service information display;

determining the attention degree of a user watching the service information to the service information according to the first multimedia information;

In the technical scheme provided by the embodiment of the application, the real user is identified by acquiring the biological characteristics of the user, which are different from other people; recommending service information according to the associated information of the real user and the scene information; therefore, the requirement that personalized recommendation can be carried out for each user when a plurality of users share one device is met. In addition, the technical scheme provided by the embodiment fully considers the scene information of the user when recommending the information, so that the recommended information has identification degree related to the scene information, and the accuracy of information recommendation is improved.

In another technical scheme provided by the embodiment of the application, for an unregistered new user, recommending information for the unregistered new user according to biological characteristics of the new user different from other people and scene information of the new user; therefore, the audience surface of the technical scheme provided by the embodiment is wider and is not limited to registered users, so that a plurality of users sharing one device can enjoy personalized recommendation service.

In still another technical scheme provided by the embodiment of the application, the attention degree of a user watching the service information to the service information is determined according to the first multimedia information by collecting the first multimedia information related to the user in the service information display; further, the portrait information of the user can be updated in time according to the attention degree of the user to the service information; the dependency on active feedback of the user is reduced, and the user portrait information is updated more timely and accurately.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an information recommendation system according to an embodiment of the present application;

fig. 2 is a schematic diagram of a theoretical structure of a server in an information recommendation system according to an embodiment of the present application;

FIG. 3 is a flowchart illustrating an information recommendation method according to an embodiment of the present application;

FIG. 4 is a flowchart illustrating an information recommendation method according to another embodiment of the present application;

FIG. 5 is a flowchart illustrating an information recommendation method according to another embodiment of the present application;

FIG. 6 is a flowchart of an information processing method according to an embodiment of the present application;

FIG. 7 is a flowchart illustrating an information recommendation method according to another embodiment of the present application;

FIG. 8 is a schematic diagram of an image information update process according to an embodiment of the present application;

FIG. 9 is a block diagram illustrating an information recommendation apparatus according to an embodiment of the present application;

FIG. 10 is a block diagram illustrating an information recommendation apparatus according to another embodiment of the present application;

FIG. 11 is a block diagram illustrating an information recommendation apparatus according to another embodiment of the present application

Fig. 12 is a block diagram of an information processing apparatus according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the application.

Detailed Description

In the prior art, there is a scheme that presumes interest preferences of a user depending on a category of service information that has a high click frequency of the user, a category of service information that the user adds to favorites or the like, or a category access path that the user is accustomed to using. The scheme directly carries out analysis and judgment according to the corresponding category of the personal operation record of the user, and the personal operation record reflects personal preference to a certain extent; such a method enables basically a user to obtain more directly the favorite program types with a certain probability.

In another existing scheme, the interest tags of each user and the text history records searched in the search box are stored, and each service information in the service information database also has a respective tag or keyword. Such methods may more targeted the recommended content of interest to the user who is actively entering his own interest tag, or who has too many search records.

The prior art scheme relies on the active operation of the user to a great extent, and for the equipment placed in the home scene, many users may be processing some households or participating in household activities at the same time, and may not touch the screen closely to perform frequent operation, and in the environment where the information security problem is more and more prominent, more users are not willing to actively input the information of the user. Therefore, in the actual operation process of the existing scheme, the coverage of the algorithm is quite narrow often because of the insufficient collection of the needed user information.

On the other hand, the above-mentioned existing scheme is mainly aimed at a device such as a mobile phone with one hand or a public device with one registered ID for each person to log in independently, but does not consider a scene that multiple users share the same device and the same management account in a family scene, so if the scheme is directly used in such a scene, the interest trends of different family members cannot be distinguished, and the situation that "mom likes a class a program" and father recommends a class a program "is easily caused. In addition, all the above existing schemes still stay in the statistics and calculation of the user's operations or text matching itself, and do not make full use of visual information such as video images for data analysis, resulting in a relatively narrow dimension of information available for use.

In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present application with reference to the accompanying drawings.

In some of the flows described in the description of the application, the claims, and the figures described above, a number of operations occurring in a particular order are included, and the operations may be performed out of order or concurrently with respect to the order in which they occur. The sequence numbers of operations such as 101, 102, etc. are merely used to distinguish between the various operations, and the sequence numbers themselves do not represent any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.

Furthermore, the embodiments described below are only some, but not all, embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Before introducing the information recommendation method provided by the application, a system architecture on which the method provided by the application is based is described.

As shown in fig. 1, a schematic structure diagram of an information recommendation system according to an embodiment of the present application is provided. As shown in fig. 1, the information recommendation system provided in this embodiment includes: client 101 and server 102. Wherein, the liquid crystal display device comprises a liquid crystal display device,

a client 101 for acquiring a biometric characteristic of a user that is different from another person; responding to the information acquisition request triggered by the user, and acquiring scene information when the request is triggered; the biological characteristics and the scene information are sent to a server;

the server 102 is configured to obtain association information related to the user when the user is determined to be a registered user based on the biometric feature; and recommending service information to the user according to the association information and the scene information.

In the technical scheme provided by the embodiment, the real user is identified by acquiring the biological characteristics of the user, which are different from other people; recommending service information according to the associated information of the real user and the scene information; therefore, the requirement that personalized recommendation can be carried out for each user when a plurality of users share one device is met. In addition, the technical scheme provided by the embodiment fully considers the scene information of the user when recommending the information, so that the recommended information has identification degree related to the scene information, and the accuracy of information recommendation is improved.

Further, the server 102 may be further configured to recommend service information to the user according to the scenario information and the biometric feature when the user is determined to be a non-registered user based on the biometric feature.

In one implementation technical solution, the server 102 is specifically configured to: when the user is determined to be a non-registered user based on the biological characteristics, determining the crowd category of the user according to the biological characteristics; and recommending service information which is interested in the crowd category in a scene corresponding to the scene information for the user according to the crowd category and the scene information. In particular implementations, the biological features may include, but are not limited to, at least one of: facial features, voiceprints, fingerprints. The scene information may include, but is not limited to: geographic location information and/or time intervals. The gender, age interval and the like of the user can be determined through the facial features, the user is classified into the crowd category with the gender in the age interval according to the gender and the age interval, and then service information is recommended for the user according to the preference of the crowd category in the corresponding scene of the scene information.

Alternatively, the server 102 may be specifically configured to: when the user is determined to be a non-registered user based on the biological characteristics, building association information for the user according to the biological characteristics; and recommending service information to the user according to the association information and the scene information. In the implementation, the association information may be portrait information. In general, for non-registered users, the server side does not record and count the behavior data generated by the non-registered users at the client side; here, building the association information can be simply understood as: the implicit registration for the non-registered user is convenient for the subsequent user to acquire and store the behavior data of the user for updating and perfecting the associated information when the user generates the behavior data at the client side; and further, the accuracy of information recommendation is continuously improved.

Of course, the server 102 provided in this embodiment may also perform display registration for a non-registered user, that is, the server 102 may be further configured to: when the user is determined to be a non-registered user based on the biometric feature, a registered account is created for the user based on the biometric feature to collect behavioral data of the user.

In this embodiment, the client may be hardware integrated on the terminal and having an embedded program, or may be an application software installed in the terminal, or may be a tool software embedded in an operating system of the terminal, which is not limited in this embodiment of the present application. The terminal can be any terminal equipment including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant ), an intelligent wearable equipment and the like.

In addition, the associated information related to the user mentioned in the present embodiment may be portrait information. Portrayal information is an important application of big data technology, which contains descriptive labels for users in many dimensions; the tag attributes can be used for outlining real personal characteristics of multiple aspects of users, further, requirements of the users can be mined by using portrait information of the users, and preferences of the users are analyzed to recommend service information of interests of the users. The data sources used to create the user's portrayal information may include all data related to the user; through continuous accumulation and classification of data, a statistical rule of data distribution in classification categories can be obtained, and the statistical rule is correspondingly used as a descriptive label. Specifically, the data sources for creating the portrait information of the user may include: natural data, behavioral data, and content data. Wherein, the liquid crystal display device comprises a liquid crystal display device,

The natural data represents the inherent attribute of the user including the user name (registered name), sex, age, etc. of the user; can be obtained in links such as user registration and the like; for non-registered users, basic attributes such as gender, age interval and the like of the users can be determined by acquiring the biological characteristics of the users and then based on the biological characteristics.

The behavior data describes behavior performed by the user, which may include operational behavior such as: searching, browsing, scoring, ordering, collecting, adding to a shopping cart, deleting from a shopping cart, ordering, paying attention, etc.; actions in the real scene may also be included, such as: actions, facial expressions, languages, etc. of the user while viewing the service information. The operation behavior can be collected by the client and uploaded to the server; the actions in the real scene may be captured by a camera and/or microphone of the client device.

The content data represents an object of user behavior, for example, attribute information of collected service information, attribute information of service information of interest, and the like.

Descriptive labels can be established to form portrait information of users by classifying natural data, behavior data, content data and the like of users into categories in a classification system and counting the distribution of the data in the categories. After the data related to the user reaches a sufficient degree of intensity, the descriptive label attribute of the user will show a higher stability, and it is through this stability that the match with the real personal characteristics formed by the user for a long time is achieved.

The overall theoretical structure of the server in this embodiment will be described below with reference to a specific implementation example. As shown in fig. 2, it is mainly composed of seven core parts: the system comprises a content library, a portrait information module, a statistical distribution model, a user identification module, a recall algorithm module, a sorting algorithm module and a feedback module.

(1) Content library: including all content that can be recommended (e.g., system built-in video/native APP content/collaborative third party push content, etc.), as well as comprehensive depictions and metrics of category attributes, crowd preferences, and statistical features of such content.

(2) And an image information module: including portrait information for each user. In addition, as the data sources corresponding to the users accumulate, interest bias analysis based on time distribution can be gradually established, for example, sub-portraits of the users in different time intervals can be obtained. Assume that the interest areas of a certain user Top3 are: music, movies, and news; news-like programs are focused on most between 8 and 9 in the morning; the music programs are the most concerned in weekday evenings, and the movies programs are the most concerned in weekend evenings. Thus, for this user, respective sub-images may be constructed for different time intervals.

(3) Statistical distribution model: and according to the portrait information of all users, statistics is carried out regularly, and a big data interest distribution map of all users is established. It can have the following dimensions: gender, age, geographic location, time period, field of interest. The corresponding mathematical expression is:

P{(S，A，P，T，H)＝(s _i ,a _j ,p _k ,t _m ,h _n )}＝P _i,j,k,m,n

i＝0,1；j,k,m,n＝0,1,2,…

wherein S, A, P, T, H represent gender, age, geographic location, time period, and field of interest, respectively.

(4) And a user identification module: one approach is that the biometric of the user is determined by the client based on locally acquired video information, voice or fingerprint, etc.; the client then sends the user's biometric characteristics to the user identification module of the server. The user identification module identifies the biological characteristics, if the identified user is a registered user, the identification result can be sent to the portrait information module, and the portrait information of the user is found by the portrait information module according to the identification result. The other scheme is that the client directly sends the collected video information, audio information, fingerprint information and the like to a user identification module of the server; if the information sent by the client contains video information, the user identification module can process each frame of image until finding out the frame with the face, or can process every n frames (for example, n can be set as 2,3,4,5, … …); after a video frame with a face is found, face recognition is carried out on the face in the frame image, and facial features are obtained; if the information sent by the client contains audio information, after the voice segment is found in the audio information, the voice segment is identified to obtain voiceprint characteristics. If the information sent by the client contains fingerprint information, the fingerprint information is the biological characteristics of the user.

(5) A recall algorithm module: the module selects a recommendation candidate set (for example, hundreds to thousands of programs with graphics or video display) from a content library according to the portrait information of the user and scene information (time interval and/or geographical position information) of the user. In specific implementation, the recall algorithm module can be realized by adopting a classical collaborative filtering model or a theme model and the like.

(6) And the accurate ordering module performs unified scoring ordering on the contents of the plurality of recall channels and selects the optimal small number of results. Because the recommended content given during the recall phase may be an integrated result from different recall models, not strictly comparable to each other, and because the amount of data is too large to make more accurate preference and quality assessment, uniform and accurate scoring of recall results during the precise ranking phase is required. In particular, the precise ordering module may be implemented by using the prior art, which is not specifically limited in this embodiment.

(7) Feedback model: the module is used for evaluating the attention degree of the user to the service information in the display in response to the user's watching response to the service information. Wherein the user's viewing response may be determined based on capturing video and/or speech of the user's viewing in real time, etc. Specific determination steps will be described below.

The specific workflow of each component unit in the information output system, such as the server and the client, and the signaling interaction between each component unit in the information output system provided by the embodiment of the present application will be further described in the following embodiments.

Fig. 3 is a flowchart illustrating an information recommendation method according to an embodiment of the present application. The method provided by the embodiment is suitable for the server. The server may be a common server, a cloud end, a virtual server, etc., which is not particularly limited in the embodiment of the present application. As shown in fig. 3, the method provided in this embodiment includes:

201. and acquiring biological characteristics of the user, which are different from other people, and scene information of the user.

202. And acquiring association information related to the user when the user is determined to be a registered user based on the biological characteristics.

203. And recommending service information to the user according to the association information and the scene information.

In the above 201, the biometric feature includes at least one of: facial features, voiceprints, fingerprints. The scene information includes, but is not limited to: geographical location information and/or time intervals, etc. The biometric characteristic may be directly sent by the client, or may be obtained by performing characteristic recognition on video information, audio information, fingerprint information and the like sent by the client.

In one embodiment, the step 201 may be specifically: and receiving information sent by the client. When the information contains video information, the video information is detected frame by frame until a video frame with a face is found, or n frames can be detected once (for example, n can be set as 2,3,4,5 and … …); after finding out the video frame with the face, judging whether the image quality of the video frame meets the requirement of an identification algorithm; if the requirements of the recognition algorithm are met, the face recognition is carried out on the found video frames so as to obtain facial features. When the information contains audio information, detecting the audio information until an audio segment with voice appears is found; the found audio segment is identified to obtain voiceprint features. When the information contains fingerprint information, the fingerprint information can be directly used as a biological feature.

In 203, the related information related to the user may be portrait information of the user. In one implementation solution, the step 203 may specifically include the following steps:

2031. and acquiring the sub-image corresponding to the scene information from the image information.

2032. And recommending service information to the user according to the sub-portraits.

The recommendation algorithm employed in step 2032 may include a collaborative filtering algorithm, among other things. The collaborative filtering algorithm comprises: user-based collaborative filtering algorithms, item-based collaborative filtering algorithms, and the like. Wherein, based on collaborative filtering algorithm of user: this algorithm recommends to the user what other users like that which is similar to his interests. Collaborative filtering algorithm based on articles: this algorithm recommends to the user items similar to the items he liked before. Of course, the topic model may also be employed to implement recommendation of service information. In particular, the specific implementation of the collaborative filtering algorithm, the topic model, etc. can be referred to the related content in the prior art, and will not be described herein.

Further, the method provided in this embodiment may further include:

204. and identifying the basic attribute of the user according to the biological characteristics.

205. And when the sample library is provided with a sample matched with the biological characteristics, acquiring user information corresponding to the matched sample.

206. And when the basic attribute is matched with the user information, determining that the user is a registered user.

In the above 204, the basic attribute includes at least one of the following: gender, age range, etc.

In an embodiment of the present application, the biological features may include: facial features, voiceprints, fingerprints, etc. Facial features may be the user's nose, mouth, eyes, wrinkles, hair, or other feature information of some face, etc. The age range of the user may be determined by identifying characteristics of the user such as skin roughness, skin aging, depth of wrinkles, or length of wrinkles. The sex of the user may be determined by identifying the user's makeup, hair length, etc. Of course, the gender and age range of the user may also be obtained by analyzing voiceprints.

Further, the method provided in this embodiment may further include the following steps:

207. And recommending service information to the user according to the scene information and the biological characteristics when the user is determined to be a non-registered user based on the biological characteristics.

In one implementation solution, the "recommending service information for the user according to the scene information and the biometric feature" in step 207 may include the following steps:

2071. and determining the crowd category of the user according to the biological characteristics.

2072. And recommending service information which is interested in the crowd category in a scene corresponding to the scene information for the user according to the crowd category and the scene information.

208. when the user is determined to be a non-registered user based on the biometric feature, a registered account is created for the user based on the biometric feature to collect behavioral data of the user.

Wherein the purpose of collecting behavior data of the user is to refine portrayal information of the user.

Fig. 4 is a flowchart illustrating an information recommendation method according to another embodiment of the present application. The method provided by the embodiment is suitable for the client. The client may be hardware integrated on the terminal and provided with an embedded program, or may be an application software installed in the terminal, or may be a tool software embedded in an operating system of the terminal, which is not limited in the embodiment of the present application. The terminal can be any terminal equipment including a mobile phone, a tablet personal computer, intelligent wearable equipment, AR equipment and the like. As shown in fig. 4, the information recommendation method includes:

301. The biometric features of the user that are different from others are obtained.

302. And responding to the information acquisition request triggered by the user, and acquiring scene information when the request is triggered.

303. And sending the biological characteristics and the scene information to a server, so that the server recommends service information for the user according to the biological characteristics and the scene information.

In one implementation solution, the above 301 may include:

3011. at least one of face images, voices and fingerprints of a user are collected.

3012. And determining the biological characteristics according to at least one of the face image, the voice and the fingerprint.

The determination of the biological characteristics in 3012 may be referred to in the related art, and will not be described herein.

In 302 above, the information acquisition request may be triggered when the user opens the application home page; or triggered after the user clicks the corresponding control key (such as an entity control key or a virtual control key on a remote controller or a mobile phone); or may be triggered after the user makes a specified voice, etc., which is not particularly limited by the embodiment of the present application.

Fig. 5 is a flowchart illustrating an information recommendation method according to another embodiment of the present application. The method provided by the embodiment is suitable for the server. The server may be a common server, a cloud end, a virtual server, etc., which is not particularly limited in the embodiment of the present application. As shown in fig. 5, the information recommendation method includes:

401. and acquiring biological characteristics of the user, which are different from other people, and scene information of the user.

402. And when the user is determined to be a non-registered user based on the biological characteristics, building association information for the user according to the biological characteristics.

403. And recommending service information to the user according to the association information and the scene information.

In 402 above, building association information for a user can be simply understood as: the implicit registration for the non-registered user is convenient for the subsequent user to acquire and store the behavior data of the user for updating and perfecting the associated information when the user generates the behavior data at the client side; and further, the accuracy of information recommendation is continuously improved. In particular, the associated information may be portrait information.

In the technical scheme provided by the embodiment, for an unregistered new user, recommending information is provided for the unregistered new user according to biological characteristics of the new user different from other people and scene information of the new user; therefore, the audience surface of the technical scheme provided by the embodiment is wider and is not limited to registered users, so that a plurality of users sharing one device can enjoy personalized recommendation service.

In one possible technical solution, the step 402 of "building association information for the user according to the biometric feature" may be implemented specifically as follows:

4021. and identifying the basic attribute of the user according to the biological characteristics.

4022. And constructing the portrait information for the user according to the basic attribute.

For example, based on the biometric characteristics (e.g., facial characteristics, voiceprints, etc.), the gender, age-section, etc. of the user is identified; and calling a big data statistical map, and taking the gender, age interval and the like of the user as input to initialize portrait information of the user. In the specific implementation, the information such as the gender, the age interval and the like of the user is used as a search keyword, and interest tags of other users with the same gender and the same age interval are inquired in the big data statistical map; common interest tags that most of these users (more than a threshold number of users) have are then added to the portrayal information as interest tags for the users.

404. and creating a registered account for the user according to the biological characteristics so as to collect behavior data of the user.

405. And updating the portrait information according to the collected behavior data of the user.

In practical application, the behavior data of the user includes: dominant feedback data and implicit feedback data; wherein the explicit feedback data includes behavior data triggered by the user and indicating interest in service information, such as praise, scoring high, good evaluation, attention, etc.; the implicit feedback data comprises behavior data which is triggered by the user and cannot clearly indicate whether the user is interested, for example, video information and/or audio information and the like when the user views service information are acquired. For explicit feedback data in the behavior data, the portrait information of the user can be updated directly based on the explicit attention to the service information of the display feedback data. And for implicit feedback data in the behavior data, analyzing the implicit feedback data to evaluate the attention degree of the user to the service information according to an analysis result, and updating the portrait information of the user according to the evaluated attention degree of the user to the service information.

For example, the behavior data of the user includes: and the first service information displays the first multimedia information acquired in the first service information display. Accordingly, the step 405 may be implemented as follows:

4051. And evaluating the attention degree of the user to the first service information according to the first multimedia information.

4052. And updating the portrait information according to the attention degree of the user to the first service information and the attribute information of the first service information.

Wherein the first multimedia information may comprise first video information and/or first audio information.

In one implementation, the first multimedia information may include first video information. Accordingly, this step 4051 may be implemented as follows:

s11, monitoring the face direction and the sight direction of the user according to the first video information;

and S12, evaluating the attention degree of the user to the first service information according to the face direction and the sight line direction.

The face orientation of the user may be calculated by using a head pose estimation algorithm, and in implementation, the face orientation may be represented by a ternary vector (Roll, pitch, yaw), where Roll, pitch, yaw respectively represent angles of rotation of the face of the user about x-axis, y-axis, and z-axis of a reference coordinate system. The reference coordinate system may be a default coordinate system of the image acquisition module, or may be a manually set coordinate, which is not specifically limited in this embodiment. It should be noted that, the head pose estimation algorithm is in the prior art, and specific implementation can be referred to relevant content of the prior art, which is not described herein.

In S12, a period of time for focusing the user on the screen may be determined according to the face direction and the line of sight direction; and according to the determined duration, the attention degree of the user to the first service information can be evaluated. In general, the longer the user focuses on the screen, the higher the user's focus on the information presented on his screen.

In another implementation manner, the first multimedia information may include first video information. Accordingly, this step 4051 may be implemented as follows:

s21, acquiring the frame number of a first video frame containing the user image from the first video information, and recording the frame number as a first number;

s22, counting the number of frames of the user, of which the sight direction meets the first requirement, according to a first video frame containing the user image, and marking the number as a second number;

s23, calculating the attention degree of the user to the first service information according to the first number and the second number.

For example, a degree of interest of the user in the first service information is calculated based on a ratio of the second number to the first number. Can be simply understood as: in all video frames appearing to the user, the more the number of frames the user focuses on the screen, the higher the attention degree of the user to the first service information currently displayed on the screen is; in contrast, the fewer the number of frames in which the user's line of sight focuses on the screen, the lower the user's attention to the first service information currently displayed on the screen, among all the video frames in which the user appears. Therefore, the attention degree of the user to the first service information can be determined through the value interval of the ratio of the second number to the first number. Each value space corresponds to a numerical attention.

In still another implementation manner, the first multimedia information includes first audio information in addition to the first video information. Accordingly, the present step 4051 may further include the following steps:

s24, acquiring the number of segments of the first voice segment with the voiceprint characteristics of the user from the first audio information, and recording the number as a fifth number;

s25, counting the number of the voice segments meeting the second requirement according to the number of the first voice segments with the voice print characteristics of the user, and recording the number as a sixth number;

s26, according to the fifth number and the sixth number, the attention degree of the user to the first service information is updated.

Of course, when the first multimedia information includes only the first audio information, the step S26 may specifically be: and calculating the attention degree of the user to the first service information according to the fifth number and the sixth number.

For example, the speech segment meeting the second requirement may be a speech segment containing speech words indicating the interest of the user, or a speech segment containing "haha" like words, etc. In a specific implementation, the attention degree of the user to the first service information may be calculated according to the ratio of the sixth number to the fifth number. The same can be understood simply as: the more voice segments which are in accordance with the second requirement appear in voice segments which are made by the user, the higher the attention degree of the user to the first service information currently displayed on the screen is; and conversely, the user has low attention to the first service information currently displayed on the screen.

Therefore, the higher the evaluation accuracy can be if the first video information and the first audio information can be combined.

Further, the behavior data of the user may further include: the first service information displays the second multimedia information which is collected before and related to the user. Accordingly, the above step 4051 should be modified to 4051':

4051', evaluating the user's attention to the first service information based on the first multimedia information and the second multimedia information.

In one implementation solution, the first multimedia information includes first video information; the second multimedia information includes second video information. Accordingly, the step 4051' may include:

s31, acquiring the number of frames of a second video frame containing the user image from the second video information, and recording the number as a first number;

s32, counting the number of frames of the user, of which the sight direction meets the first requirement, according to a second video frame containing the user image, and marking the number as a second number;

s33, acquiring the frame number of a first video frame containing the user image from the first video information, and recording the frame number as a third number;

s34, counting the number of frames, which are in line of sight of the user and meet the first requirement, according to the first video frames containing the user images, and recording the number as a fourth number;

S35, calculating the attention degree of the user to the first service information according to the first number, the second number, the third number and the fourth number.

For example, count ₁₁ A first number; count (count) ₁₂ A second number; count (count) ₂₁ A third number; count (count) ₂₂ A fourth number. When count ₁₁ Not equal to 0 and count ₂₁ When not equal to 0, the attention value interval_value may be calculated as follows:

if count ₂₂ =0, then let interval_value=0 directly;

otherwise the first set of parameters is selected,

/>

still further, the first multimedia information further includes first audio information; the second multimedia information further includes second audio information. Accordingly, and accordingly, step 4051' above may further include:

s36, acquiring the number of segments of a second voice segment with the voiceprint characteristics of the user from the second audio information, and recording the number as a fifth number;

s37, counting the number of the voice segments meeting the second requirement according to the number of the second voice segments with the voice print characteristics of the user, and recording the number as a sixth number;

s38, acquiring the number of segments of the first voice segment with the voiceprint characteristics of the user from the first audio information, and recording the number as a seventh number;

s39, counting the number of the voice segments meeting the second requirement according to the first voice segment with the voice print characteristics of the user, and recording the number as an eighth number;

S310, according to the fifth number, the sixth number, the seventh number and the eighth number, the attention of the user to the first service information is updated.

And the fifth number, the sixth number, the seventh number, the eighth number and the attention of the user to the first service information are all used as inputs of the update calculation model, and the existing attention can be updated by executing the update calculation model. Updating (which may be simply understood as modifying) the attention in conjunction with the audio information helps to provide accuracy in the calculation of the attention. The method comprises the steps of carrying out a first treatment on the surface of the In addition, the updated calculation model can be obtained by self-defining according to the actual application requirement, which is not particularly limited in this embodiment.

406. and synchronizing the updated portrait information to a big data interest distribution map so as to update the corresponding content of the big data interest distribution map.

Fig. 6 is a flowchart of an information processing method according to an embodiment of the application. The method provided by the embodiment is suitable for the client. The client may be hardware integrated on the terminal and provided with an embedded program, or may be an application software installed in the terminal, or may be a tool software embedded in an operating system of the terminal, which is not limited in the embodiment of the present application. The terminal can be any terminal equipment including a mobile phone, a tablet personal computer, intelligent wearable equipment, AR equipment and the like. As shown in fig. 6, the information processing method includes:

501. First multimedia information related to a user in service information presentation is collected.

502. And determining the attention degree of the user watching the service information to the service information according to the first multimedia information.

503. And sending the attention degree of the user to the service information to a server so as to update the portrait information of the user according to the attention degree of the user to the service information by the server.

In 501, the first multimedia information related to the user may be acquired by an image acquisition module (such as a camera) of the client device. Taking a mobile phone as an example, the first multimedia information related to the user can be acquired by a front camera of the mobile phone.

The specific implementation of 502 may refer to the corresponding content in the method embodiment, which is not described herein.

In the technical scheme provided by the embodiment, the attention degree of a user watching service information to the service information is determined according to first multimedia information by collecting the first multimedia information related to the user in service information display; further, the portrait information of the user can be updated in time according to the attention degree of the user to the service information; the dependency on active feedback of the user is reduced, and the user portrait information is updated more timely and accurately.

In 502 above, the multimedia information includes: video information and/or audio information.

504. and collecting second multimedia information related to the user before the service information is displayed.

Accordingly, the step 502 should be specifically:

502', determining the attention degree of the user watching the service information to the service information according to the first multimedia information and the second multimedia.

As can be seen from the methods provided in the above embodiments, the technical solution provided by the present application mainly includes two parts: the first part is a personalized recommendation; the second part is an update of the portrait information.

First part, information recommendation

Fig. 7 is a flowchart illustrating an information recommendation method according to another embodiment of the present application. Referring to fig. 7, the following is described in detail:

601. the client acquires the current geographic position and the time interval.

602. The client acquires video information and performs face detection on the video information to detect video frames with face images.

603. The client judges whether the image quality of the video frame with the face image meets the requirement of an identification algorithm; if yes, go to step 604; otherwise, returning to step 602, the video information is continuously collected.

604. And the client extracts facial features of the user closest to the acquisition module and sends the facial feature data to the server.

In the implementation, the information with privacy in the facial features can be removed and then sent to the server.

605. The server side identifies the gender and age interval of the user according to the facial features; comparing the facial features with samples in a registered face library; if there are samples in the registered face library that match the facial features, then step 606 is performed; otherwise, step 609 is performed.

606. The server side invokes the user ID corresponding to the sample; performing secondary matching with the user information corresponding to the ID through the gender and the age interval; if the secondary matching is successful, determining that the user is a registered user, and executing steps 607-608; otherwise, steps 609 to 610 are performed.

607. The server side calls a recall algorithm module, and selects a recommendation candidate set (for example, hundreds to thousands of programs with graphics and texts or video display) from a content library according to the portrait information of the user and scene information (such as geographical position information, time interval and the like) of the user.

608. And the server performs scoring sorting on the candidate service information in the recommended candidate set given by the recall algorithm module, and selects the optimal small quantity of results.

The candidates obtained in the recall stage are all the content of interest to the user, but the collection is relatively large, and the sorting stage performs more accurate calculation on the basis, so that a small amount of high-quality content of most interest to the user is selected from thousands of candidates. And finally outputting one or more recommended contents according to the service requirement.

609. The server end completes implicit automatic registration for the user, marks the user as a new user in the interaction process for subsequent flow.

610. The server calls a big data statistical map of the server, takes gender and age interval of the user based on facial feature recognition, scene information of the user and the like as input, and recommends the content which is most possibly interested in the user.

According to the technical scheme provided by the embodiment, the user identity is automatically matched through face recognition, gender and age judgment and the like on the acquired real-time video information so as to conduct personalized recommendation for specific user individuals. In addition, under the condition that the user does not have explicit registration, the device can still memorize the user through the collected video information automatic clustering, so that the audience of the personalized recommendation algorithm is wider and is not limited to actively registered users.

Second part 2, updating of portrait information

The specific flowchart 8 shows that the method comprises the following steps:

701. the server initializes its portrayal information for each new user.

In the implementation, the server can call a big data statistical map, and uses the gender, the age interval and the geographical position information and the time interval of the new user as input to initialize the portrait information of the new user.

702. If the user is a new user actively registered, the server needs to combine the interest tag selected by the actively registered user with the portrait information initialized for the user.

The combination method can be selected by self, and a simpler mode is to superimpose the interest tag selected by the user into the initial personal portrait information in a weighted mode.

703. The client starts an image acquisition device (such as a front camera of a mobile phone) to acquire video information in real time, and sends the acquired video information to the server.

704. The server invokes a head pose estimation algorithm in a feedback module (as shown in fig. 2) to detect in real-time the user's face orientation at this time (e.g., which may be characterized by the angle of the face relative to the screen).

In particular, the user face orientation may be represented by a ternary vector (Roll, pitch, yaw), where Roll, pitch, yaw represent the angle of rotation of the user face about the x-axis, y-axis, and z-axis, respectively.

705. The server invokes a gaze tracking algorithm in a feedback module (shown in fig. 2) to track the user's eye movements in real time to analyze whether the user's gaze is focused on the screen at this time.

706. And (5) integrating the face orientation of the user and the focusing time of the sight on the screen, and evaluating the attention degree of the user to the screen display content.

The specific evaluation method can be customized according to actual requirements, and the following is an example of the method:

a. before a screen displays a certain content, counting the number of frames in which people appear in a video frame sequence through a human body detection and face detection algorithm, and marking as follows: count (count) ₁₁ ；

b. Before the screen displays a certain content, the number of frames with intersection of the video line direction and the screen in the video frame sequences appearing by people is counted and is recorded as count ₁₂ ；

c. In the process of displaying a certain content on a screen, the video frame sequence is counted through human body detection and face detection algorithmsThe number of frames in the column in which a person appears is noted: count (count) ₂₁ ；

d. In the process of displaying a certain content on a screen, counting the number of frames with intersection of the video line direction and the screen in the video frame sequences, wherein the number is recorded as follows: count (count) ₂₂ ；

e. When count ₁₁ Not equal to 0 and count ₂₁ If not equal to 0, counting the attention degree interval_value of the user to the current screen content according to the following method;

If count ₂₂ =0, then let interval_value=0 directly;

otherwise the first set of parameters is selected,

707. and the server updates the portrait information of the user according to the attention degree of the user to the screen display content.

What needs to be explained here is: the steps 704 to 706 may be performed by a client, that is, the client performs the steps 704 to 706 to obtain the attention degree of the user to the screen display content, and then feeds back the attention degree of the user to the screen display content to the server, so that the server updates the portrait information of the user based on the attention degree of the user to the screen display content.

708. And the server synchronously feeds back the updating of the portrait information of the user to the big data interest distribution map so as to update the corresponding content of the big data interest distribution map.

According to the technical scheme provided by the embodiment, whether the sight of the user is focused on the screen or not is analyzed in real time through the algorithms such as head gesture estimation, sight tracking and the like, and the degree of focus of the user on the screen display content is intelligently estimated. On the intelligent equipment with screen, a series of visual intelligent analysis algorithms such as the above are added in the two-way process of personalized recommendation and user feedback acquisition, so that the application can solve the problems: the method solves the problems that when the intelligent hardware product with the screen in the home scene recommends the visual content, the active feedback of the user is insufficient, and the recommendation model is difficult to optimize only by passively receiving the user feedback by the equipment.

Fig. 9 is a block diagram showing a configuration of an information recommendation apparatus according to an embodiment of the present application. As shown in fig. 9, the information recommendation apparatus includes: the first acquisition module 11, the second acquisition module 12 and the recommendation module 13. The first obtaining module 11 is configured to obtain a biological feature of a user different from another person and scene information of the user; the second obtaining module 12 is configured to obtain association information related to the user when the user is determined to be a registered user based on the biometric feature; the recommending module 13 is configured to recommend service information to the user according to the association information and the scene information.

Further, the biometric features include at least one of: facial features, voiceprints, fingerprints.

Further, the information recommendation device may further include: the device comprises an identification module, a third acquisition module and a determination module. The identification module is used for identifying the basic attribute of the user according to the biological characteristics; the third acquisition module is used for acquiring user information corresponding to the matched sample when the sample matched with the biological characteristic exists in the sample library; and the determining module is used for determining that the user is a registered user when the basic attribute is matched with the user information.

Further, the basic attribute includes at least one of: gender, age interval.

Further, the scene information includes: geographic location information and/or time information.

Further, the associated information is portrait information; correspondingly, the recommendation module 13 is further configured to obtain a sub-portrait corresponding to the scene information from the portrait information; and recommending service information to the user according to the sub-portraits.

Further, the recommendation module 13 is further configured to recommend service information to the user according to the scenario information and the biometric feature when the user is determined to be a non-registered user based on the biometric feature.

Further, the recommendation information 13 is further used for: determining the crowd category of the user according to the biological characteristics; and recommending service information which is interested in the crowd category in a scene corresponding to the scene information for the user according to the crowd category and the scene information.

Further, the device provided in this embodiment further includes: a module is created. The creation module is used for creating a registered account for the user according to the biological characteristics so as to collect behavior data of the user when the user is determined to be a non-registered user based on the biological characteristics.

What needs to be explained here is: the information recommending apparatus provided in the foregoing embodiments may implement the technical solutions described in the foregoing method embodiments, and the specific implementation principles of the foregoing modules or units may refer to corresponding contents in the foregoing method embodiments, which are not described herein again.

Fig. 10 is a block diagram showing an information recommendation apparatus according to another embodiment of the present application. As shown in fig. 10, the information recommendation apparatus includes: the acquisition module 21 and the transmission module 22. Wherein the acquisition module 21 is used for acquiring biological characteristics of the user, which are different from other people; and responding to the information acquisition request triggered by the user, and acquiring scene information when the request is triggered. The sending module 22 is configured to send the biometric feature and the scene information to a server, so that the server recommends service information for the user according to the biometric feature and the scene information.

Further, the acquiring module 21 is further configured to acquire at least one of a face image, voice and fingerprint of the user; and determining the biological characteristics according to at least one of the face image, the voice and the fingerprint.

Fig. 11 is a block diagram showing a structure of an information recommending apparatus according to still another embodiment of the present application. As shown in fig. 11, the information recommendation apparatus includes: the system comprises an acquisition module 31, a construction module 32 and a recommendation module 33. The acquiring module 31 is configured to acquire a biological feature of a user different from another person and scene information of the user; the construction module 32 is configured to construct association information for the user according to the biometric feature when the user is determined to be a non-registered user based on the biometric feature; the recommending module 33 is configured to recommend service information to the user according to the association information and the scene information.

Further, the construction module 32 is further configured to identify a basic attribute of the user according to the biometric feature; and constructing the portrait information for the user according to the basic attribute.

Further, the device provided in this embodiment further includes: the module is created and updated. The creation module is used for creating a registration account for the user according to the biological characteristics so as to collect behavior data of the user; and the updating module is used for updating the portrait information according to the collected behavior data of the user.

Further, the behavior data of the user includes: the first multimedia information related to the user is acquired in the first service information display; correspondingly, the updating module is further configured to:

According to the first multimedia information, evaluating the attention degree of the user to the first service information;

and updating the portrait information according to the attention degree of the user to the first service information and the attribute information of the first service information.

Further, the first multimedia information includes first video information; correspondingly, the updating module is further configured to:

according to the first multimedia information, evaluating the attention degree of the user to the first service information, including:

monitoring the face direction and the sight direction of the user according to the first video information;

and evaluating the attention degree of the user to the first service information according to the face direction and the sight direction.

Still further, the behavior data of the user further includes: the first service information displays the second multimedia information which is collected before and related to the user; correspondingly, the updating module is further configured to:

and evaluating the attention degree of the user to the first service information according to the first multimedia information and the second multimedia information.

Further, the first multimedia information and the second multimedia information each include: video information and/or audio information.

Further, the first multimedia information includes first video information; the second multimedia information includes second video information; correspondingly, the updating module is further configured to:

acquiring the number of frames of a second video frame containing the user image from the second video information, and recording the number as a first number;

counting the number of frames of the user, which accords with the first requirement, according to a second video frame containing the user image, and recording the number as a second number;

acquiring the frame number of a first video frame containing the user image from the first video information, and recording the frame number as a third number;

counting the number of frames, which are in line with the first requirement, of the user sight direction according to the first video frame containing the user image, and recording the number as a fourth number;

and calculating the attention degree of the user to the first service information according to the first number, the second number, the third number and the fourth number.

Further, the first multimedia information further includes first audio information; the second multimedia information further includes second audio information, and correspondingly, the update module is further configured to:

acquiring the number of segments of a second voice segment with the voiceprint characteristics of the user from the second audio information, and recording the number as a fifth number;

Counting the number of the voice segments meeting the second requirement according to the number of the second voice segments with the voice print characteristics of the user, and recording the number as a sixth number;

acquiring the number of segments of a first voice segment with the voiceprint characteristics of the user from the first audio information, and recording the number as a seventh number;

counting the number of the voice segments meeting the second requirement according to the first voice segment with the voice print characteristics of the user, and recording the number as an eighth number;

and updating the attention of the user to the first service information according to the fifth number, the sixth number, the seventh number and the eighth number.

Further, the apparatus provided in this embodiment may further include a synchronization module. The synchronization module is used for synchronizing the updated portrait information into a big data interest distribution map so as to update the corresponding content of the big data interest distribution map.

Fig. 12 is a block diagram showing the structure of an information processing apparatus according to an embodiment of the present application. As shown in fig. 12, the information processing apparatus includes: acquisition module 41, determination module 42 and transmission module 43. Wherein, the acquisition module 41 is used for acquiring multimedia information before and during service information display; the determining module 42 is configured to determine, according to the first multimedia information, a degree of attention of a user viewing the service information to the service information. The sending module 43 is configured to send the attention degree of the user to the service information to a server, so that the server updates the portrait information of the user according to the attention degree of the user to the service information.

In the technical scheme provided by the embodiment of the application, the attention degree of a user watching service information to the service information is determined according to the first multimedia information by collecting the first multimedia information related to the user in the service information display; further, the portrait information of the user can be updated in time according to the attention degree of the user to the service information; the dependency on active feedback of the user is reduced, and the user portrait information is updated more timely and accurately.

Further, the multimedia information includes: video information and/or audio information.

What needs to be explained here is: the information processing apparatus provided in the foregoing embodiments may implement the technical solutions described in the foregoing method embodiments, and the specific implementation principles of the foregoing modules or units may refer to corresponding contents in the foregoing method embodiments, which are not repeated herein.

Fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 13, the electronic device includes a memory 51 and a processor 52, wherein,

the memory 51 is used for storing a program;

the processor 52 is coupled to the memory 51 for executing the program stored in the memory 51 for:

The processor 52 may realize other functions in addition to the above functions when executing the program in the memory 51, and the above description of the embodiments can be specifically referred to.

Further, as shown in fig. 13, the electronic device further includes: communication component 53, display 54, power component 55, audio component 56, and other components. Only some of the components are schematically shown in fig. 13, which does not mean that the electronic device only comprises the components shown in fig. 13.

An embodiment of the application provides a client device. The implementation structure of the client device provided in this embodiment is similar to the structure shown in fig. 13 described above. The client device provided in this embodiment includes: memory and processor, wherein

The memory is used for storing programs;

The processor may perform other functions in addition to the above functions when executing the program in the memory, and the foregoing description of the embodiments may be specifically referred to.

Further, the client device further includes: communication components, power components, audio components, and the like.

Another embodiment of the application provides an electronic device. The implementation structure of the electronic device provided in this embodiment is similar to the structure shown in fig. 13 described above. The electronic device provided in this embodiment includes: comprising a memory and a processor, wherein,

The memory is used for storing programs;

Further, the electronic device further includes: communication components, power components, audio components, and the like.

Another embodiment of the present application provides a client device. The implementation structure of the client device provided in this embodiment is similar to the structure shown in fig. 13 described above. The client device provided in this embodiment includes: a memory and a processor, wherein,

the memory is used for storing programs;

The memory in the above embodiments may be configured to store various other data to support operations on the client device. Examples of such data include instructions for any application or method operating on a client device. The memory may be implemented by any type of volatile or nonvolatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

Accordingly, the embodiments of the present application also provide a computer-readable storage medium storing a computer program, where the computer program when executed by a computer can implement the steps or functions of the information recommendation method provided in the foregoing embodiments.

The embodiments of the present application also provide a computer-readable storage medium storing a computer program which, when executed by a computer, can implement the steps or functions of the information processing method provided in each of the above embodiments.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An information recommendation method, comprising:

recommending service information to the user according to the association information and the scene information;

before the first service information is displayed, second multimedia information related to a user is collected; the second multimedia information includes second video information;

in the first service information display, first multimedia information related to a user is collected; the second multimedia information includes first video information;

calculating the attention degree of the user to the first service information according to the first number, the second number, the third number and the fourth number;

and updating the associated information according to the attention degree and the attribute information of the first service information.

2. The method of claim 1, wherein the biometric features comprise at least one of: facial features, voiceprints, fingerprints.

3. The method as recited in claim 1, further comprising:

identifying basic attributes of the user according to the biological characteristics;

When a sample matched with the biological characteristics exists in the sample library, acquiring user information corresponding to the matched sample;

and when the basic attribute is matched with the user information, determining that the user is a registered user.

4. A method according to claim 3, wherein the basic properties include at least one of: gender, age interval.

5. The method according to any one of claims 1 to 4, wherein the scene information includes: geographic location information and/or time intervals.

6. The method according to any one of claims 1 to 4, wherein the associated information is portrait information; and

recommending service information to the user according to the association information and the scene information, wherein the service information comprises the following steps:

acquiring a sub-image corresponding to the scene information from the image information;

and recommending service information to the user according to the sub-portraits.

7. The method according to any one of claims 1 to 4, further comprising:

and recommending service information to the user according to the scene information and the biological characteristics when the user is determined to be a non-registered user based on the biological characteristics.

8. The method of claim 7, wherein recommending service information for the user based on the context information and the biometric feature comprises:

determining the crowd category of the user according to the biological characteristics;

and recommending service information which is interested in the crowd category in a scene corresponding to the scene information for the user according to the crowd category and the scene information.

9. The method as recited in claim 7, further comprising:

when the user is determined to be a non-registered user based on the biometric feature, a registered account is created for the user based on the biometric feature to collect behavioral data of the user.

10. An information recommendation method, comprising:

the biological characteristics and the scene information are sent to a server, so that the server obtains association information related to the user according to the biological characteristics, and service information is recommended to the user according to the association information and the scene information;

when the association information is updated, acquiring the number of frames of a second video frame containing the user image from the second video information, and recording the number as a first number; counting the number of frames of the user, which accords with the first requirement, according to a second video frame containing the user image, and recording the number as a second number; acquiring the frame number of a first video frame containing the user image from the first video information, and recording the frame number as a third number; counting the number of frames, which are in line with the first requirement, of the user sight direction according to the first video frame containing the user image, and recording the number as a fourth number; calculating the attention degree of the user to the first service information according to the first number, the second number, the third number and the fourth number; and updating the associated information according to the attention degree and the attribute information of the first service information.

11. The information recommendation method according to claim 10, wherein acquiring a biometric characteristic of a user that is different from others, comprises:

collecting at least one of face images, voices and fingerprints of a user;

and determining the biological characteristics according to at least one of the face image, the voice and the fingerprint.

12. An information recommendation system, comprising:

the server side is used for acquiring association information related to the user when the user is determined to be a registered user based on the biological characteristics; recommending service information to the user according to the association information and the scene information;

the server is also used for acquiring second multimedia information related to the user before the first service information is displayed; the second multimedia information includes second video information; in the first service information display, first multimedia information related to a user is collected; the second multimedia information includes first video information; acquiring the number of frames of a second video frame containing the user image from the second video information, and recording the number as a first number; counting the number of frames of the user, which accords with the first requirement, according to a second video frame containing the user image, and recording the number as a second number; acquiring the frame number of a first video frame containing the user image from the first video information, and recording the frame number as a third number; counting the number of frames, which are in line with the first requirement, of the user sight direction according to the first video frame containing the user image, and recording the number as a fourth number; calculating the attention degree of the user to the first service information according to the first number, the second number, the third number and the fourth number; and updating the associated information according to the attention degree and the attribute information of the first service information.

13. The system of claim 12, wherein the system further comprises a controller configured to control the controller,

the server side is further configured to recommend service information to the user according to the scene information and the biometric feature when the user is determined to be a non-registered user based on the biometric feature.

14. An information recommendation method, comprising:

15. The method of claim 14, wherein constructing association information for the user based on the biometric feature comprises:

and constructing the association information for the user according to the basic attribute.

16. The method of claim 14, wherein the associated information is portrait information, and

the method further comprises the steps of:

creating a registered account for the user based on the biometric feature to collect behavioral data of the user;

and updating the portrait information according to the collected behavior data of the user.

17. The method of claim 14, wherein the first multimedia information further comprises first audio information; the second multimedia information further includes second audio information, and

according to the first multimedia information and the second multimedia information, evaluating the attention degree of the user to the first service information comprises the following steps:

18. The method as recited in claim 16, further comprising:

And synchronizing the updated portrait information to a big data interest distribution map so as to update the corresponding content of the big data interest distribution map.

19. An information processing method, characterized by comprising:

collecting first multimedia information related to a user in service information display; the first multimedia information includes first video information;

before the service information is displayed, second multimedia information related to a user is collected; the second multimedia information includes second video information;

calculating the attention degree of the user to the service information according to the first number, the second number, the third number and the fourth number;

And sending the attention degree of the user to the service information to a server side so that the server side updates the portrait information of the user according to the attention degree of the user to the service information and the attribute information of the service information.

20. The method of claim 19, wherein the first multimedia information further comprises first audio information; the second multimedia information further includes second audio information, and

the method further comprises the steps of:

and updating the attention of the user to the service information according to the fifth number, the sixth number, the seventh number and the eighth number.

21. An electronic device comprising a memory and a processor, wherein,

the memory is used for storing programs;

22. A client device comprising a memory and a processor, wherein,

the memory is used for storing programs;

23. An electronic device comprising a memory and a processor, wherein,

the memory is used for storing programs;

24. A client device comprising a memory and a processor, wherein,

the memory is used for storing programs;